Slashdot Mirror
MIT Is Improving Object Recognition For Robots
jan_jes writes: MIT have demonstrated their monocular SLAM supported approach that is able to achieve stronger performance against the classical frame based approach [where misclassifications occur occasionally]. The system is able to detect and robustly recognize objects in its environment using a single RGB camera. They have presented their paper at the Robotics Science and Systems conference last week. The system uses SLAM information to augment existing object-recognition algorithms. Robot with camera provide the improved object predictions in all views.
Because this is how you get Terminators.
Robots will do a better job and not require Cheetos or a soft drink.
Where are the news here?
As a researcher in this field not affiliated with this work, the merit is that most SLAM methods (that's essentially mapping an environment and tracking your position within it) have generally had very little understanding of the map that results. The world is most commonly a fuzzy blob of pixels or voxels.
In contrast, a human might "map" an environment in terms of salient objects, like "The potted plant" or a set of office chair. Such a semantic map has several possible advantages--- it could support more natural interactions with people, and it can serve as a powerful regularizer that prevents the robot from learning incorrect maps.
The particular method described in this paper is pretty well executed, and making a system that runs in real time with such a large amount of data is not easy. Of course, many researchers are looking at building semantic maps.
I thought SLAM was a program to deny food to poor people.. "Suspected of Living Above Means".
I should use this sig to advertise my book ISBN-13 : 978-1501515132.
Psst, hey, editors -- it's always a good idea to spell out acronyms when they're first used if they're unfamiliar to those outside the article's specialty.